Perception Machine Learning Engineer

Waymo is an autonomous driving technology company with the mission to be the world's most trusted driver. Since its start as the Google Self-Driving Car Project in 2009, Waymo has focused on building the Waymo Driver—The World's Most Experienced Driver™—to improve access to mobility while saving thousands of lives now lost to traffic crashes. The Waymo Driver powers Waymo’s fully autonomous ride-hail service and can also be applied to a range of vehicle platforms and product use cases. The Waymo Driver has provided over ten million rider-only trips, enabled by its experience autonomously driving over 100 million miles on public roads and tens of billions in simulation across 15+ U.S. states.

As a Perception Machine Learning Engineer, you will build the intelligent systems that "see" the world, directly shaping the future of autonomous travel.

Within the Perception team, we are tackling some of the most complex, open-ended challenges in autonomous driving. Our models must constantly adapt and improve as our fleet encounters the vast, unpredictable realities of public roads. We are looking for a Machine Learning Engineer to help design and build the automated, closed-loop systems that drive this continuous improvement.

In this role, you will be the bridge between model architecture and large-scale data infrastructure. You will leverage active learning and sophisticated data curation strategies to ensure our perception models are always learning from the most informative examples. Crucially, this means managing the entire lifecycle of our data: intelligently selecting novel scenarios from the fleet while continuously pruning our existing corpus to maximize training efficiency.

In this hybrid role you will report to a Technical Lead Manager.

You will:

• Architect Infrastructure: Design and scale the data pipelines needed to mine, ingest, and manage massive volumes of sensor data from our fleet.
• Drive Model Improvement: Deploy active learning algorithms to continuously identify and select the most impactful data for training, ensuring our large models continuously adapt to new environments with incremental updates.
• Ensure Model Quality: Develop methods and recipes for evaluating real-world performance of our models, and detecting regressions in model updates.  Develop and maintain ground-truth free performance metrics.
• Optimize Data Efficiency: Conduct large-scale experiments focused on data balancing, subset selection, and label quality optimization. Lead automated curation strategies—including smart pruning and downsampling—to minimize dataset bloat and maximize compute efficiency.
• Develop robust mining, training and evaluation pipelines for rare, safety-critical real-world scenarios.